INDEX

Explanations

references to various paths and directions individuals or groups can take toward achieving goals or navigating challenges

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ´ŀ

-0.14

Î»Î±Î½

-0.14

ingers

-0.14

imers

-0.14

à¸Ńà¸²à¸ģà¸²à¸¨

-0.13

indice

-0.13

ece

-0.13

 turno

-0.13

Ø±ÙĪÙģ

-0.13

rani

-0.13

POSITIVE LOGITS

 path

0.38

path

0.32

 paths

0.31

-path

0.30

/path

0.29

 Path

0.29

=path

0.29

[path

0.28

(path

0.27

.path

0.27

Activations Density 0.069%

references to various paths and directions individuals or groups can take toward achieving goals or navigating challenges

No Comments

No Known Activations